基于分类层级逐步训练，生成高精度细粒度动物图像。
TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation
- 按分类等级分步训练，从纲到种逐级细化特征
- 少量样本下仍能生成形态与物种身份准确的图像
- 适合需要高精度物种级图像生成的研究场景
我们提出TaxaDiffusion，一种融合分类学知识的扩散模型训练框架，用于生成具有高形态和身份准确性的细粒度动物图像。与将每个物种视为独立类别标准方法不同，TaxaDiffusion利用许多物种存在强烈视觉相似性、差异常体现在形状、图案和颜色的细微变化这一先验知识。为此，TaxaDiffusion在不同分类层级上逐步训练条件扩散模型——从纲、目等宏观分类开始，逐步细化至科、属，最终实现物种级别区分。该分层学习策略先捕捉共享祖先物种的粗粒度形态特征，促进知识迁移，再精炼物种间的细微差异。实验在三个细粒度动物数据集上验证，结果表明其优于现有方法，在有限每物种训练样本条件下仍能实现更优的生成保真度。
原文摘要 · Abstract (English)
We propose TaxaDiffusion, a taxonomy-informed training framework for diffusion models to generate fine-grained animal images with high morphological and identity accuracy. Unlike standard approaches that treat each species as an independent category, TaxaDiffusion incorporates domain knowledge that many species exhibit strong visual similarities, with distinctions often residing in subtle variations of shape, pattern, and color. To exploit these relationships, TaxaDiffusion progressively trains conditioned diffusion models across different taxonomic levels -- starting from broad classifications such as Class and Order, refining through Family and Genus, and ultimately distinguishing at the Species level. This hierarchical learning strategy first captures coarse-grained morphological traits shared by species with common ancestors, facilitating knowledge transfer before refining fine-grained differences for species-level distinction. As a result, TaxaDiffusion enables accurate generation even with limited training samples per species. Extensive experiments on three fine-grained animal datasets demonstrate that outperforms existing approaches, achieving superior fidelity in fine-grained animal image generation. Project page: https://amink8.github.io/TaxaDiffusion/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。